Volumetrically Consistent Implicit Atlas Learning via Neural Diffeomorphic Flow for Placenta MRI
This addresses the problem of group-level analysis in medical imaging, specifically for placenta MRI, by enabling voxel-wise intensity mapping in a unified canonical space, though it is incremental as it builds on existing implicit registration methods.
The paper tackled the problem of establishing dense volumetric correspondences across anatomical shapes in implicit neural representations, which was challenging due to under-constrained interior deformations in existing methods. The result was a volumetrically consistent implicit model that improved geometric fidelity and volumetric alignment over surface-based baselines in placenta MRI scans, yielding anatomically interpretable and topologically consistent flattening.
Establishing dense volumetric correspondences across anatomical shapes is essential for group-level analysis but remains challenging for implicit neural representations. Most existing implicit registration methods rely on supervision near the zero-level set and thus capture only surface correspondences, leaving interior deformations under-constrained. We introduce a volumetrically consistent implicit model that couples reconstruction of signed distance functions (SDFs) with neural diffeomorphic flow to learn a shared canonical template of the placenta. Volumetric regularization, including Jacobian-determinant and biharmonic penalties, suppresses local folding and promotes globally coherent deformations. In the motivating application to placenta MRI, our formulation jointly reconstructs individual placentas, aligns them to a population-derived implicit template, and enables voxel-wise intensity mapping in a unified canonical space. Experiments on in-vivo placenta MRI scans demonstrate improved geometric fidelity and volumetric alignment over surface-based implicit baseline methods, yielding anatomically interpretable and topologically consistent flattening suitable for group analysis.